baby mynah — accent experts
Collection
LoRA accent adapters for VoxCPM-0.5B and the Space that morphs between them. One small bird, many English accents. • 10 items • Updated
baby mynah — American accent (LoRA for VoxCPM-0.5B)
A LoRA adapter that voices VoxCPM-0.5B in the American accent of a single VCTK speaker. One of the accent experts behind the baby mynah Space, where you can slide between any two of them in weight space.
What it is
- Base model:
openbmb/VoxCPM-0.5B(OpenBMB), a tokenizer-free TTS model. This repo holds only the LoRA delta (~28 MB) — you also need the base model. - Accent: American (California), learned from a single VCTK speaker (p300, age 23, female) — ~8 minutes of read speech.
- Not PEFT. VoxCPM uses a custom
LoRALinear, so this loads through the baby-mynah loader, notpeft. The weights file stores, per target Linear,<prefix>.lora_A(r, in) and<prefix>.lora_B(out, r); the layer appliesout += (alpha/r) * (x @ A^T @ B^T).
Training
| Method | LoRA (rank 32, alpha 32, dropout 0) |
| Target modules | q/k/v/o_proj on both the LM and the DiT |
| Steps | 800 (effective batch 4 = batch 1 x grad-accum 4) |
| LR | 1e-4, 50 warmup, weight decay 0.01 |
| Audio | ~8 min, 16 kHz mono |
Usage
These adapters are meant to be blended, which is what the Space does. To load
one on its own, use the project's load_adapter / blend_into_model helpers
(see scripts/blend.py):
from blend import load_adapter, blend_into_model, restore_weights, scaling_from_config
from voxcpm import VoxCPM
model = VoxCPM.from_pretrained(hf_model_id="openbmb/VoxCPM-0.5B", optimize=False, device="cuda")
adapter = load_adapter("path/to/this/adapter") # {prefix: (A, B)}
scaling = scaling_from_config("path/to/this/adapter") # alpha / r
# alpha=1.0 applies this expert fully; restore afterwards (surgery is in-place).
snap = blend_into_model(model.tts_model, adapter, adapter, alpha=1.0, scaling=scaling)
wav = model.generate(text="Hello! I am a very small bird.", normalize=True)
restore_weights(model.tts_model, snap)
License & attribution
- LoRA weights released under CC BY 4.0, following the VCTK corpus (CSTR, University of Edinburgh) they were trained on.
- Base model VoxCPM-0.5B by OpenBMB, Apache-2.0.
import soundfile as sf from voxcpm import VoxCPM model = VoxCPM.from_pretrained("build-small-hackathon/baby-mynah-american") wav = model.generate( text="VoxCPM is an innovative end-to-end TTS model from ModelBest, designed to generate highly expressive speech.", prompt_wav_path=None, # optional: path to a prompt speech for voice cloning prompt_text=None, # optional: reference text cfg_value=2.0, # LM guidance on LocDiT, higher for better adherence to the prompt, but maybe worse inference_timesteps=10, # LocDiT inference timesteps, higher for better result, lower for fast speed normalize=True, # enable external TN tool denoise=True, # enable external Denoise tool retry_badcase=True, # enable retrying mode for some bad cases (unstoppable) retry_badcase_max_times=3, # maximum retrying times retry_badcase_ratio_threshold=6.0, # maximum length restriction for bad case detection (simple but effective), it could be adjusted for slow pace speech ) sf.write("output.wav", wav, 16000) print("saved: output.wav")